Mastra における Voice

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { OpenAIVoice } from "@mastra/voice-openai";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new OpenAIVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
speaker: "default", // Optional: specify a speaker
responseFormat: "wav", // Optional: specify a response format
});
 
playAudio(audioStream);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { AzureVoice } from "@mastra/voice-azure";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new AzureVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: "en-US-JennyNeural", // Optional: specify a speaker
});
 
playAudio(audioStream);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { ElevenLabsVoice } from "@mastra/voice-elevenlabs";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new ElevenLabsVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
speaker: "default", // Optional: specify a speaker
});
 
playAudio(audioStream);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { PlayAIVoice } from "@mastra/voice-playai";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new PlayAIVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: "default", // Optional: specify a speaker
});
 
playAudio(audioStream);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { GoogleVoice } from "@mastra/voice-google";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new GoogleVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
speaker: "en-US-Studio-O", // Optional: specify a speaker
});
 
playAudio(audioStream);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { CloudflareVoice } from "@mastra/voice-cloudflare";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new CloudflareVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: "default", // Optional: specify a speaker
});
 
playAudio(audioStream);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { DeepgramVoice } from "@mastra/voice-deepgram";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new DeepgramVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
speaker: "aura-english-us", // Optional: specify a speaker
});
 
playAudio(audioStream);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { SpeechifyVoice } from "@mastra/voice-speechify";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new SpeechifyVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: "matthew", // Optional: specify a speaker
});
 
playAudio(audioStream);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { SarvamVoice } from "@mastra/voice-sarvam";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new SarvamVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
speaker: "default", // Optional: specify a speaker
});
 
playAudio(audioStream);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { MurfVoice } from "@mastra/voice-murf";
import { playAudio } from "@mastra/node-audio";
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new MurfVoice(),
});
 
const { text } = await voiceAgent.generate('What color is the sky?');
 
// テキストを音声に変換し、オーディオストリームを生成
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: "default", // 任意: 話者を指定
});
 
playAudio(audioStream);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { OpenAIVoice } from "@mastra/voice-openai";
import { createReadStream } from 'fs';
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new OpenAIVoice(),
});
 
// URL からの音声ファイルを使用
const audioStream = await createReadStream("./how_can_i_help_you.mp3");
 
// 音声をテキストに変換
const transcript = await voiceAgent.voice.listen(audioStream);
console.log(`User said: ${transcript}`);
 
// 文字起こしに基づいて応答を生成
const { text } = await voiceAgent.generate(transcript);
 

import { createReadStream } from 'fs';
import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { AzureVoice } from "@mastra/voice-azure";
import { createReadStream } from 'fs';
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new AzureVoice(),
});
 
// URL からの音声ファイルを使用
const audioStream = await createReadStream("./how_can_i_help_you.mp3");
 
// 音声をテキストに変換
const transcript = await voiceAgent.voice.listen(audioStream);
console.log(`User said: ${transcript}`);
 
// 文字起こしに基づいて応答を生成
const { text } = await voiceAgent.generate(transcript);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { ElevenLabsVoice } from "@mastra/voice-elevenlabs";
import { createReadStream } from 'fs';
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new ElevenLabsVoice(),
});
 
// URL からの音声ファイルを使用
const audioStream = await createReadStream("./how_can_i_help_you.mp3");
 
// 音声をテキストに変換
const transcript = await voiceAgent.voice.listen(audioStream);
console.log(`User said: ${transcript}`);
 
// 文字起こしに基づいて応答を生成
const { text } = await voiceAgent.generate(transcript);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { GoogleVoice } from "@mastra/voice-google";
import { createReadStream } from 'fs';
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new GoogleVoice(),
});
 
// URL からの音声ファイルを使用
const audioStream = await createReadStream("./how_can_i_help_you.mp3");
 
// 音声をテキストに変換
const transcript = await voiceAgent.voice.listen(audioStream);
console.log(`User said: ${transcript}`);
 
// 文字起こしに基づいて応答を生成
const { text } = await voiceAgent.generate(transcript);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { CloudflareVoice } from "@mastra/voice-cloudflare";
import { createReadStream } from 'fs';
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new CloudflareVoice(),
});
 
// URL から取得した音声ファイルを使用
const audioStream = await createReadStream("./how_can_i_help_you.mp3");
 
// 音声をテキストに変換
const transcript = await voiceAgent.voice.listen(audioStream);
console.log(`User said: ${transcript}`);
 
// テキストに基づいて応答を生成
const { text } = await voiceAgent.generate(transcript);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { DeepgramVoice } from "@mastra/voice-deepgram";
import { createReadStream } from 'fs';
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new DeepgramVoice(),
});
 
// URL から取得した音声ファイルを使用
const audioStream = await createReadStream("./how_can_i_help_you.mp3");
 
// 音声をテキストに変換
const transcript = await voiceAgent.voice.listen(audioStream);
console.log(`User said: ${transcript}`);
 
// テキストに基づいて応答を生成
const { text } = await voiceAgent.generate(transcript);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { SarvamVoice } from "@mastra/voice-sarvam";
import { createReadStream } from 'fs';
 
const voiceAgent = new Agent({
name: "Voice Agent",
instructions: "You are a voice assistant that can help users with their tasks.",
model: openai("gpt-4o"),
voice: new SarvamVoice(),
});
 
// URL から取得した音声ファイルを使用
const audioStream = await createReadStream("./how_can_i_help_you.mp3");
 
// 音声をテキストに変換
const transcript = await voiceAgent.voice.listen(audioStream);
console.log(`User said: ${transcript}`);
 
// テキストに基づいて応答を生成
const { text } = await voiceAgent.generate(transcript);
 

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { playAudio, getMicrophoneStream } from '@mastra/node-audio';
import { OpenAIRealtimeVoice } from "@mastra/voice-openai-realtime";
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new OpenAIRealtimeVoice(),
});
 
// Listen for agent audio responses
voiceAgent.voice.on('speaker', ({ audio }) => {
  playAudio(audio);
});
 
// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?');
 
// Send continuous audio from the microphone
const micStream = getMicrophoneStream();
await voiceAgent.voice.send(micStream);

import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
import { playAudio, getMicrophoneStream } from '@mastra/node-audio';
import { GeminiLiveVoice } from "@mastra/voice-google-gemini-live";
 
const voiceAgent = new Agent({
  name: "Voice Agent",
  instructions: "You are a voice assistant that can help users with their tasks.",
  model: openai("gpt-4o"),
  voice: new GeminiLiveVoice({
    // Live API mode
    apiKey: process.env.GOOGLE_API_KEY,
    model: 'gemini-2.0-flash-exp',
    speaker: 'Puck',
    debug: true,
    // Vertex AI alternative:
    // vertexAI: true,
    // project: 'your-gcp-project',
    // location: 'us-central1',
    // serviceAccountKeyFile: '/path/to/service-account.json',
  }),
});
 
// Connect before using speak/send
await voiceAgent.voice.connect();
 
// Listen for agent audio responses
voiceAgent.voice.on('speaker', ({ audio }) => {
  playAudio(audio);
});
 
// Listen for text responses and transcriptions
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`);
});
 
// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?');
 
// Send continuous audio from the microphone
const micStream = getMicrophoneStream();
await voiceAgent.voice.send(micStream);

// OpenAI Voice の設定
const voice = new OpenAIVoice({
  speechModel: {
    name: "gpt-3.5-turbo", // 例: モデル名
    apiKey: process.env.OPENAI_API_KEY,
    language: "en-US", // 言語コード
    voiceType: "neural", // 音声モデルのタイプ
  },
  listeningModel: {
    name: "whisper-1", // 例: モデル名
    apiKey: process.env.OPENAI_API_KEY,
    language: "en-US", // 言語コード
    format: "wav", // 音声フォーマット
  },
  speaker: "alloy", // 例: 話者名
});

// Azure Voice の設定
const voice = new AzureVoice({
  speechModel: {
    name: "en-US-JennyNeural", // 例: モデル名
    apiKey: process.env.AZURE_SPEECH_KEY,
    region: process.env.AZURE_SPEECH_REGION,
    language: "en-US", // 言語コード
    style: "cheerful", // ボイスタイル
    pitch: "+0Hz", // ピッチ調整
    rate: "1.0", // 話速
  },
  listeningModel: {
    name: "en-US", // 例: モデル名
    apiKey: process.env.AZURE_SPEECH_KEY,
    region: process.env.AZURE_SPEECH_REGION,
    format: "simple", // 出力形式
  },
});

// ElevenLabs Voice の設定
const voice = new ElevenLabsVoice({
  speechModel: {
    voiceId: "your-voice-id", // 例: ボイスID
    model: "eleven_multilingual_v2", // 例: モデル名
    apiKey: process.env.ELEVENLABS_API_KEY,
    language: "en", // 言語コード
    emotion: "neutral", // 感情設定
  },
  // ElevenLabs にはリスニングモデルが別途ない場合があります
});

// PlayAI Voice の設定
const voice = new PlayAIVoice({
  speechModel: {
    name: "playai-voice", // 例: モデル名
    speaker: "emma", // 例: 話者名
    apiKey: process.env.PLAYAI_API_KEY,
    language: "en-US", // 言語コード
    speed: 1.0, // 発話速度
  },
  // PlayAI にはリスニングモデルが別途ない場合があります
});

// Google Voice の設定
const voice = new GoogleVoice({
  speechModel: {
    name: "en-US-Studio-O", // 例: モデル名
    apiKey: process.env.GOOGLE_API_KEY,
    languageCode: "en-US", // 言語コード
    gender: "FEMALE", // 声質（性別）
    speakingRate: 1.0, // 発話速度
  },
  listeningModel: {
    name: "en-US", // 例: モデル名
    sampleRateHertz: 16000, // サンプルレート
  },
});

// Cloudflare Voice の設定
const voice = new CloudflareVoice({
  speechModel: {
    name: "cloudflare-voice", // 例: モデル名
    accountId: process.env.CLOUDFLARE_ACCOUNT_ID,
    apiToken: process.env.CLOUDFLARE_API_TOKEN,
    language: "en-US", // 言語コード
    format: "mp3", // 音声フォーマット
  },
  // Cloudflare にはリスニングモデルが別途ない場合があります
});

// Deepgram Voice の構成
const voice = new DeepgramVoice({
  speechModel: {
    name: "nova-2", // モデル名の例
    speaker: "aura-english-us", // 話者名の例
    apiKey: process.env.DEEPGRAM_API_KEY,
    language: "en-US", // 言語コード
    tone: "formal", // 口調設定
  },
  listeningModel: {
    name: "nova-2", // モデル名の例
    format: "flac", // 音声フォーマット
  },
});

// Speechify Voice の構成
const voice = new SpeechifyVoice({
  speechModel: {
    name: "speechify-voice", // モデル名の例
    speaker: "matthew", // 話者名の例
    apiKey: process.env.SPEECHIFY_API_KEY,
    language: "en-US", // 言語コード
    speed: 1.0, // 話速
  },
  // Speechify には別途リスニングモデルがない場合があります
});

// Sarvam Voice の構成
const voice = new SarvamVoice({
  speechModel: {
    name: "sarvam-voice", // モデル名の例
    apiKey: process.env.SARVAM_API_KEY,
    language: "en-IN", // 言語コード
    style: "conversational", // スタイル設定
  },
  // Sarvam には別途リスニングモデルがない場合があります
});

// Murf Voice の構成
const voice = new MurfVoice({
  speechModel: {
    name: "murf-voice", // モデル名の例
    apiKey: process.env.MURF_API_KEY,
    language: "en-US", // 言語コード
    emotion: "happy", // 感情設定
  },
  // Murf には別途リスニングモデルがない場合があります
});

// OpenAI Realtime Voice の構成
const voice = new OpenAIRealtimeVoice({
  speechModel: {
    name: "gpt-3.5-turbo", // モデル名の例
    apiKey: process.env.OPENAI_API_KEY,
    language: "en-US", // 言語コード
  },
  listeningModel: {
    name: "whisper-1", // モデル名の例
    apiKey: process.env.OPENAI_API_KEY,
    format: "ogg", // 音声フォーマット
  },
  speaker: "alloy", // 話者名の例
});

// Google Gemini Live Voice の構成
const voice = new GeminiLiveVoice({
  speechModel: {
    name: "gemini-2.0-flash-exp", // モデル名の例
    apiKey: process.env.GOOGLE_API_KEY,
  },
  speaker: "Puck", // 話者名の例
  // Google Gemini Live は、音声生成とリスニングのモデルが分かれていない双方向リアルタイム API です
});